Cover......Page 1
Half Title......Page 2
Title Page......Page 6
Copyright Page......Page 7
Table of Contents......Page 8
Preface......Page 14
1.1 Brief History of Artificial Intelligence......Page 18
1.2.2 Second Wave: Statistical Machine Learning......Page 21
1.2.3 Third Wave: Contextual Adaptation......Page 23
1.2.4 The Last Wave: Artificial General Intelligence......Page 24
1.3.1 Data Science......Page 25
1.3.2 Supervised Learning: Classification and Regression......Page 26
1.3.3 Unsupervised Learning: Clustering and Association......Page 27
1.3.4 Reinforcement Learning......Page 28
1.3.5 Swarm Intelligence......Page 29
1.3.6 Evolutionary Learning......Page 31
1.4 Summary......Page 32
1.5 Problems......Page 33
2.1.1 Structured and Unstructured Data......Page 34
2.1.2 Random Variation and Its Causes......Page 36
2.1.3 Internal and External Validities......Page 37
2.1.5 Bias, Bias, and Bias......Page 38
2.1.6 Confounding Factors......Page 40
2.1.7 Regression to the Mean......Page 42
2.2.1 Innovative and Adaptive Development Program......Page 43
2.2.2 Control, Blinding, and Randomization......Page 44
2.3.1 Statistical Hypothesis Testing......Page 45
2.3.2 Generalized Linear Model......Page 47
2.3.3 Air Quality Analysis with Generalized Linear Model......Page 49
2.3.4 Lung Cancer Survival Analysis with Cox's Model......Page 51
2.3.5 Propensity Score Matching......Page 52
2.4.1 Decision Approach......Page 53
2.4.2 Regularization......Page 54
2.4.3 Subset Selection......Page 55
2.4.4 Real-World Examples......Page 56
2.5.1 General Steps in Applying Machine Learning......Page 57
2.5.2 Cross-Validation......Page 58
2.6 Summary......Page 61
2.7 Problems......Page 62
3.1.1 Dilemma of Totality Evidence with p-Value......Page 66
3.1.2 Multiple-Testing Versus Multiple-Learning......Page 67
3.1.3 A Medical and Judicial Tragedy......Page 68
3.1.4 Simpson's Paradox......Page 69
3.1.5 Bias in Predicting Drug Effectiveness......Page 70
3.2.1 Role of Similarity Principle......Page 71
3.2.2 The Root of Causality......Page 73
3.3.1 Attributes Selection......Page 76
3.3.3 Cosine Similarity and Jaccard Index......Page 77
3.3.4 Distance-Based Similarity Function......Page 79
3.3.5 Similarity and Dissimilarity of String and Signal Data......Page 81
3.3.7 Similarix......Page 82
3.3.8 Adjacency Matrix of Network......Page 84
3.4 Summary......Page 85
3.5 Problems......Page 86
4.1.1 Nearest-Neighbors Method for Supervised Learning......Page 88
4.1.2 Similarity-Based Learning......Page 90
4.1.3 Similarity Measures......Page 91
4.1.4 Algorithms for SBML......Page 92
4.1.5 Prediction Error Decomposition......Page 95
4.1.6 Training, Validation, and Test Datasets......Page 96
4.2.2 Loss Function......Page 97
4.2.3 Computer Implementation......Page 101
4.3 Case Studies......Page 103
4.4 Different Outcome Variables......Page 104
4.5.2 Missing Data Handling......Page 105
4.5.5 Ensemble Methods and Collective Intelligence......Page 106
4.5.7 Dimension Reduction......Page 107
4.5.8 Recursive SBML......Page 108
4.7 Summary......Page 111
4.8 Problems......Page 114
5.1 Hebb's Rule and McCulloch-Pitts Neuronal Model......Page 116
5.2.1 Model Construction......Page 118
5.2.2 Perceptron Learning......Page 120
5.2.3 Linear Separability......Page 121
5.3.1 Model Construction......Page 123
5.3.2 Gradient Method......Page 124
5.4 Artificial Neural Network with R......Page 126
5.4.1 ANN for Infertility Modeling......Page 128
5.4.2 Feedforward Network with Karasr Package......Page 131
5.4.3 MNIST Handwritten Digits Recognition......Page 133
5.5 Summary......Page 137
5.6 Problems......Page 138
6.1 Deep Learning and Software Packages......Page 140
6.2.1 Ideas Behind CNN......Page 141
6.2.3 Deep Learning Architecture......Page 142
6.2.4 Illustration of CNN with Example......Page 143
6.2.5 CNN for Medical Image Analysis......Page 147
6.2.6 A CNN for Handwritten Digits Recognition......Page 148
6.2.7 Training CNN Using Keras in R......Page 150
6.3.1 Short-Term Memory Network......Page 154
6.3.2 An Example of RNN in R......Page 156
6.3.3 Long Short-Term Memory Networks......Page 158
6.3.4 Sentiment Analysis Using LSTMs in R......Page 161
6.3.5 Applications of LSTMs in Molecular Design......Page 166
6.4 Deep Belief Networks......Page 168
6.4.1 Restricted Boltzmann machine......Page 169
6.4.2 Application of Deep Belief Networks......Page 171
6.5 Generative Adversarial Networks......Page 172
6.6 Autoencoders......Page 174
6.7 Summary......Page 175
6.8 Problems......Page 177
7.1 Subject Representation Using Kernels......Page 178
7.2 Prediction as Weighted Kernels......Page 180
7.3.1 Hard-Margin Model......Page 181
7.3.3 R Program for Support Vector Machine......Page 184
7.4 Feature and Kernel Selections......Page 186
7.5 Application of Kernel Methods......Page 188
7.6 Dual Representations......Page 189
7.8 Problems......Page 190
8.1 Classification Tree......Page 192
8.2 Regression Tree......Page 198
8.3 Bagging and Boosting......Page 200
8.4 Random Forests......Page 203
8.5 Summary......Page 204
8.6 Problems......Page 205
9.1 Bayesian Paradigms......Page 206
9.2.1 Bayesian Network for Molecular Similarity Search......Page 209
9.2.2 Coronary Heart Disease with Bayesian Network......Page 211
9.3.1 Basic Formulations......Page 214
9.3.2 Preclinical Study of Fluoxetine on Time Immobile......Page 219
9.4 Model Selection......Page 222
9.5 Hierarchical Model......Page 223
9.6 Bayesian Decision-Making......Page 225
9.7 Summary and Discussion......Page 226
9.8 Problems......Page 227
10.2 Association or Link Analysis......Page 228
10.3 Principal Components Analysis......Page 229
10.4 K-Means Clustering......Page 232
10.5 Hierarchical Clustering......Page 235
10.6 Self-Organizing Maps......Page 238
10.7 Network Clustering and Modularity......Page 244
10.8 Unsupervised to Supervised Learning......Page 248
10.9 Summary......Page 249
10.10 Problems......Page 250
11.1 Introduction......Page 252
11.2.1 Descriptive and Normative Decision-Making......Page 253
11.2.2 Markov Chain......Page 254
11.2.3 Markov Decision Process......Page 256
11.2.4 Dynamic Programming......Page 257
11.3.1 Model for Clinical Development Program......Page 260
11.3.2 Markov Decision Tree and Out-Licensing......Page 268
11.5 Bayesian Stochastic Decision Process......Page 270
11.6 Partially Observable Markov Decision Processes......Page 272
11.7 Summary......Page 274
11.8 Problems......Page 275
12.1.1 Artificial Swarm Intelligence......Page 276
12.1.2 Applications......Page 278
12.2.1 Genetic Algorithm......Page 280
12.2.2 Genetic Algorithm for Infertility......Page 281
12.2.3 Genetic Programming......Page 284
12.2.4 Application......Page 286
12.3 Cellular Automata......Page 287
12.5 Problems......Page 290
13.1.1 Deep Learning Networks......Page 292
13.1.2 Network Similarity-Based Machine Learning......Page 293
13.1.3 Kernel Method and SVMs......Page 294
13.1.4 Decision-Tree Method......Page 295
13.1.6 Comparisons with Different Methods......Page 296
13.2.1 Cancer Detection from Gene Expression Data......Page 297
13.2.3 Cancer Prediction......Page 298
13.2.4 Clustering......Page 299
13.3.1 Deep Learning for Medical Image Processing......Page 300
13.3.2 Deep Learning Methods in Mammography......Page 301
13.3.3 Deep Learning for Cardiological Image Analysis......Page 302
13.4.1 Paradigm Shift......Page 304
13.4.2 Disease Diagnosis and Prognosis......Page 305
13.4.3 Natural Language Processing in Medical Records......Page 307
13.5.1 Necessary Paradigm Shift in Clinical Trials......Page 308
13.5.2 Learning Paradigms......Page 309
13.5.3 AI in Pharmacovigilance......Page 311
13.6 Summary......Page 313
14: Future PerspectivesβArtificial General Intelligence......Page 316
15.2 AI Software Packages......Page 324
15.3 Derivatives of Similarity Functions......Page 325
15.4 Derivation of Backpropagation Algorithms for ANN......Page 326
15.5 Similarity-Based Machine Learning in R......Page 330
Bibliography......Page 334
Index......Page 362